{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/finding-the-way-from-a-to-a-sub-character-1","title":"Finding the way from ä to a: Sub-character morphological inflection for the SIGMORPHON 2018 Shared Task","arxiv_id":"1809.05742","date":"2018-09-15","proceeding":null,"authors":["Fynn Schröder","Marcel Kamlot","Gregor Billing","Arne Köhn"],"abstract":"In this paper we describe the system submitted by UHH to the\nCoNLL--SIGMORPHON 2018 Shared Task: Universal Morphological Reinflection. We\npropose a neural architecture based on the concepts of UZH (Makarov et al.,\n2017), adding new ideas and techniques to their key concept and evaluating\ndifferent combinations of parameters. The resulting system is a\nlanguage-agnostic network model that aims to reduce the number of learned edit\noperations by introducing equivalence classes over graphical features of\nindividual characters. We try to pinpoint advantages and drawbacks of this\napproach by comparing different network configurations and evaluating our\nresults over a wide range of languages.","url_abs":"http://arxiv.org/abs/1809.05742v1","url_pdf":"http://arxiv.org/pdf/1809.05742v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"finding-the-way-from-a-to-a-sub-character-1","repo_url":"https://gitlab.com/nats/sigmorphon18","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"morphological-inflection","task_name":"Morphological Inflection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}